INDEX

Explanations

references to psychology and related concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Jörg

-1.01

 CreateTagHelper

-0.94

SDC

-0.88

ampton

-0.86

 Paro

-0.86

łgorzata

-0.85

nościo

-0.83

 bounties

-0.83

 Jock

-0.82

AMR

-0.82

POSITIVE LOGITS

Kro

0.89

 ль

0.86

Kro

0.74

ın

0.73

 Buck

0.70

 Fisk

0.69

pis

0.68

úcar

0.68

 Crist

0.68

 Holland

0.67

Activations Density 0.484%

references to psychology and related concepts

No Comments

No Known Activations